期刊文献+

基于差异的图像特征描述及其在绝缘子识别中的应用 被引量:8

Features description of difference-based image and its application in insulator recognition
在线阅读 下载PDF
导出
摘要 文中提出了一种新的特征描述方法用于目标识别以及实际航拍图像的绝缘子识别。定义了一种差异的计算方法,将图像的灰度值矩阵转换为差异值矩阵,将人眼对图像灰度差异敏感度的非线性关系转换为线性关系;之后针对差异值、形状、角度等特征进行区域描述以及区域之间联合特征描述。通过实验验证,提出的描述方法可以表示图像的灰度差异、形状变化等多个特征,将新的描述方法应用到实际航拍图像中,可以实现对绝缘子的识别。 This paper proposes a new features description method for target recognition and insulator recognition in the actual aerial images. Firstly,it defines a difference calculating method,Then,it converts the gray value matrix of an image to a difference value matrix,and also converts the non-linear relationship between human eye sensitivity and differences of image gray value to a linear relationship. At last,it describes the difference value,shape,angle and other features of a region and the combined features between regions. Experiments results show that the proposed method can represent multiple features of image such as the gray differences,the shape changes,etc. The application of this new method on the actual aerial images can realize the insulator recognition.
作者 高强 杨红叶
出处 《电测与仪表》 北大核心 2015年第3期117-122,共6页 Electrical Measurement & Instrumentation
关键词 差异 隶属度 绝缘子 区域 联合特征描述 difference membership insulator region combined features description
  • 相关文献

参考文献9

二级参考文献65

共引文献213

同被引文献62

  • 1Mohamed A, Dahl G, I-Iinton G. Acoustic modeling using deep belief networks[ J ]. IEEE Transactions on Audio, Speech and Language Processing, 2012, 20(1) : 14-22.
  • 2Hanlin Goh, Nicolas Thome, Matthieu Cord. Biasing restricted bolt- zmann machines to manipulate latent selectivity and sparsity [ C ]// NIPS workshop on deep learning and unsuperdsed feature learning. 2010.
  • 3Luo Heng, Shen Ruimin, Niu Changyong, et al. Sparse group re- stricted boltzmann machines [ C ]// Proceedings of the National Con- ference on Artificial Intelligence. San Francisco: AAAI, 2011: 429-434.
  • 4Andrew Maas, Awni Harlnun, Andrew Ng. Rectifier nonlinearities improve neural network acoustic models [ C 3// Proceedings of the 30th International Conference on Machine Learning. Atlanta : JMLR, 2013.
  • 5Senior A, Xin Lei. Fine context, low-rank, softplus deep neural networks for mobile speech recognition[ C]//2014 IEEE Internation- al Conference on Acoustics, Speech and Signal Processing. Florence: ICASSP, 2014: 7644-7648.
  • 6Ranzato M, Hinton G. Modeling pixel means and covariances using factorized third-order boltzmann machines [ C ]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2010: 2551-2558.
  • 7Courville A, Bergstra J, Bengio Y. Unsupervised models of images by spike-and-slab RBMs [ C ]// Proceedings of the 28th International Conference on Machine Learning. Bellevue : ICML, 2011 : 1145-1152.
  • 8H Lee, R Grosse, R Ranganath, et al. Unsupervised learning of hi- erarchical representations with convolutional deep belief networks [ J 1. Communications of the ACM, 2011,54 (10) : 95-103.
  • 9吴凤和.基于计算机视觉测量技术的图像轮廓提取方法研究[J].计量学报,2007,28(1):18-22. 被引量:87
  • 10高文硕,郑伟伟,杨磊.运动模糊图像复原技术的改进算法[J].中国传媒大学学报(自然科学版),2010,17(1):72-76. 被引量:3

引证文献8

二级引证文献83

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部